Data Preparation

Prepare Data Generator

Model Fitting

Defining Model Architecture

#> ___________________________________________________________________________
#> Layer (type)                     Output Shape                  Param #     
#> ===========================================================================
#> input (InputLayer)               (None, 28, 28, 1)             0           
#> ___________________________________________________________________________
#> dense_flatten (Flatten)          (None, 784)                   0           
#> ___________________________________________________________________________
#> dense_1 (Dense)                  (None, 32)                    25120       
#> ___________________________________________________________________________
#> dense_1_act (LeakyReLU)          (None, 32)                    0           
#> ___________________________________________________________________________
#> dense_1_bn (BatchNormalizationV1 (None, 32)                    128         
#> ___________________________________________________________________________
#> dense_1_dp (Dropout)             (None, 32)                    0           
#> ___________________________________________________________________________
#> output (Dense)                   (None, 10)                    330         
#> ___________________________________________________________________________
#> output_bn (BatchNormalizationV1) (None, 10)                    40          
#> ___________________________________________________________________________
#> output_act (Activation)          (None, 10)                    0           
#> ===========================================================================
#> Total params: 25,618
#> Trainable params: 25,534
#> Non-trainable params: 84
#> ___________________________________________________________________________

Model Evaluation

Predict on Test Dataset

Confusion Matrix

ROC Curve

Precision-Recall Curve